DocumentCode :
3403749
Title :
A scheme integrating neural networks for real-time robotic collision detection
Author :
Ma, Heng ; Cannon, David J. ; Kumara, Soundar R T
Author_Institution :
Dept. of Ind. & Manage. Syst. Eng., Pennsylvania State Univ., University Park, PA, USA
Volume :
1
fYear :
1995
fDate :
21-27 May 1995
Firstpage :
881
Abstract :
We present a scheme incorporating neural network mappings for geometric modeling and interference determination in robotic collision detection. The scheme promises to greatly reduce the computational time associated with calculating collision points, which makes real-time obstacle avoidance more achievable. The scheme includes three modules: a geometric modeling module, a collision detection module, and a decision support module. The geometric modeling module employs the restricted Coulomb energy (RCE) paradigm to describe the spatial occupancy of a 3-D object by a number of overlapping spheres. The collision detection module receives the geometric pattern in the robot´s environment and updates the spherical representation to perform geometric computation for existence of interference. The decision support module, using neural networks, provides online information for the collision detection module. A PUMA 560 robot´s CAD model was built to test the scheme. The performances using the scheme and using the CAD model were compared and presented
Keywords :
computational complexity; neural nets; path planning; real-time systems; robots; 3-D object; CAD model; PUMA 560 robot; collision detection module; computational time; decision support module; geometric modeling module; interference determination; neural networks; overlapping spheres; real-time obstacle avoidance; real-time robotic collision detection; restricted Coulomb energy paradigm; spatial occupancy; Computational efficiency; Human robot interaction; Interference; Neural networks; Object detection; Orbital robotics; Robotics and automation; Service robots; Solid modeling; Testing;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Robotics and Automation, 1995. Proceedings., 1995 IEEE International Conference on
Conference_Location :
Nagoya
ISSN :
1050-4729
Print_ISBN :
0-7803-1965-6
Type :
conf
DOI :
10.1109/ROBOT.1995.525394
Filename :
525394
Link To Document :
بازگشت